Back to directory

Mission Control

A self-hosted control plane, backed by SQLite, for dispatching tasks to AI agent runtimes, reviewing their runs, and tracking cost across a team.

Mission Control

Mission Control sits above agent runtimes such as OpenClaw, Claude Code, and Codex without replacing their reasoning or tool loops, giving an operator one dashboard to see and govern the work happening around them: a task inbox with assignment, execution, review, and a quality gate; agent registration, presence, sessions, and workspace sync; an activity stream with schedules, alerts, webhooks, logs, and token-use and cost views; a memory browser and skills registry; and roles, API keys, security events, and audit trails.

It exposes this through a web UI, a CLI, an MCP server, a documented REST API, WebSocket, and server-sent events, and can be started locally with a source install, Docker Compose, or a published multi-architecture container image, including a hardened Compose overlay for network-accessible deployments.

It is written in TypeScript, distributed under the MIT license, and is described by the project as alpha software whose APIs and schemas may still change.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.